知识卡片

普通读书笔记卡 · 6556.a · 生成模型:GPT-6

编码器输出后验近似参数

理解等级:中级

编码器接收图像和观测标签,输出低维Normal近似分布的均值与正尺度,再从中采Z。它不是简单输出一个确定编码,也不是直接获得真实后验;近似族和优化限制会影响结果。

这张卡片看不懂?

已有反馈 · 0 条

    还没有人提交反馈。

    在整书笔记中的位置

    原书出处 · 1 处

    • · 查看原书依据

      takes as input an image, a digit label, and the is-handwritten indicator. These inputs are concatenated and passed through a series of fully connected layers with Softplus activation functions. The final output of the encoder consists of two vectors representing the location (z_loc) and scale (z_scale) parameters of the latent space distribution on Z, given observed values for image (img), digit (digit), and is-handwritten (is_handwritten).

    参考来源

    - 位置:《Causal AI》第05章《连接因果与深度学习》(来源项目:a19c7933-4eda-4176-aebd-30fe7e1ad292;源文件:extracted/Causal AI/_epub-src/OEBPS/Text/chapter-5.xhtml) - 结论依据:摘录中关于编码器输出后验近似参数的定义、比较或条件支撑卡片;原书表述不严谨的范围已在覆盖记录逐项限定,不把案例结果外推为普遍结论。 - 原始内容:takes as input an image, a digit label, and the is-handwritten indicator. These inputs are concatenated and passed through a series of fully connected layers with Softplus activation functions. The final output of the encoder consists of two vectors representing the location (z_loc) and scale (z_scale) parameters of the latent space distribution on Z, given observed values for image (img), digit (digit), and is-handwritten (is_handwritten).